Pytorch nn.Dropout的用法示例详解
目录
- 1.nn.Dropout用法一
- 2.nn.Dropout用法二
- 补充:torch.nn.dropout和torch.nn.dropout2d的区别
1.nn.Dropout用法一
一句话总结:Dropout的是为了防止过拟合而设置
详解部分:
1.Dropout是为了防止过拟合而设置的2.Dropout顾名思义有丢掉的意思3.nn.Dropout(p = 0.3) # 表示每个神经元有0.3的可能性不被激活4.Dropout只能用在训练部分而编程客栈不能用在测试部分5.Dropout一般用在全连接神经网络映射层之后,如代码的nn.Linear(20, 30)之后代码部分:
class Dropout(nn.Module): def __init__(self): super(Dropout, self).__init__() self.linear = nn.Linear(20, 40) self.dropout = nn.Dropout(p = 0.3www.devze.com) # p=0.3表编程客栈示下图(a)中的神经元有p = 0.3的概率不被激活 defandroid forward(self, inputs): out = self.linear(inputs) out = self.dropoutphp(out) return out net = Dropout() # Dropout只能用在train而不能用在test
2.nn.Dropout用法二
以代码为例
import torch import torch.nn as nn a = torch.randn(4, 4) print(a) """ tensor([[ 1.2615, -0.6423, -0.4142, 1.2982], [ 0.2615, 1.3260, -1.1333, -1.6835], [ 0.0370, -1.0904, 0.5964, -0.1530], [ 1.1799, -0.3718, 1.7287, -1.5651]]) """ dropout = nn.Dropout() b = dropout(a) print(b) """ tensor([[ 2.5230, -0.0000, -0.0000, 2.5964], [ 0.0000, 0.0000, -0.0000, -0.0000], [ 0.0000, -0.0000, 1.1928, -0.3060], [ 0.0000, -0.7436, 0.0000, -3.1303]]) """
由以上代码可知Dropout还可以将部分tensor中的值置为0
补充:torch.nn.dropout和torch.nn.dropout2d的区别
import torch import torch.nn as nn import torch.autograd as autograd m = nn.Dropout(p=0.5) n = nn.Dropout2d(p=0.5) input = autograd.Variable(torch.randn(1, 2, 6, 3)) ## 对dim=1维进行随机置为0 print(m(input)) print('****************************************************') print(n(input))
下面的都是错误解释和错误示范,没有删除的原因是留下来进行对比,希望不要犯这类错误
# -*- coding: utf-8 -*- import torch import torch.nn as nn import torch.autograd as autograd m = nn.Dropout(p=0.5) n = nn.Dropout2d(p=0.5) input = autograd.Variable(torch.randn(2, 6, 3)) ## 对dim=1维进行随机置为0 print(m(input)) print('****************************************************') print(n(input))
结果是:
可以看到torch.nn.Dropout对所有元素中每个元素按照概率0.5更改为零, 绿色椭圆,
而torch.nn.Dropout2d是对每个通道按照概率0.5置为0, 红色方框内注:我只是圈除了部分到此这篇关于Pytorch nn.Dropout的用法的文章就介绍到这了,更多相关Pytorch 开发者_C开发nn.Dropout用法内容请搜索我们以前的文章或继续浏览下面的相关文章希望大家以后多多支持我们!
精彩评论